Hands-On Deep Learning with MIT OpenCourseWare

About this path

This learning path is based on MIT's 15.773 Hands-On Deep Learning course, taught by Rama Ramakrishnan. It is a fast-paced introduction that focuses on building practical skills for solving problems with unstructured data. You will learn how to set up and train deep neural networks, use convolutional networks for images, apply transformers for natural language, and explore generative models like LLMs and text-to-image systems. The course assumes prior familiarity with Python and basic machine learning concepts such as training/validation/testing, overfitting, and regularization. All videos are from MIT OpenCourseWare and are available under a Creative Commons license.

What you will learn

• Understand the fundamentals of deep neural networks and how to train them effectively.
• Build and apply convolutional neural networks for image and video processing.
• Use transfer learning and fine-tuning to adapt pre-trained vision models.
• Understand embeddings and transformer architectures for natural language processing.
• Explore large language models, retrieval augmented generation, and parameter-efficient fine-tuning.
• Learn about text-to-image generative models and their applications.

Who this is for

Self-paced learners who want a clear free path with creator-credited YouTube lessons.

Curriculum